Division of X-Ray Imaging and Computed Tomography, German Cancer Research Center (DKFZ), Heidelberg, Germany.
Department of Physics and Astronomy, Heidelberg University, Heidelberg, Germany.
Med Phys. 2023 Sep;50(9):5312-5330. doi: 10.1002/mp.16612. Epub 2023 Jul 17.
Vascular diseases are often treated minimally invasively. The interventional material (stents, guidewires, etc.) used during such percutaneous interventions are visualized by some form of image guidance. Today, this image guidance is usually provided by 2D X-ray fluoroscopy, that is, a live 2D image. 3D X-ray fluoroscopy, that is, a live 3D image, could accelerate existing and enable new interventions. However, existing algorithms for the 3D reconstruction of interventional material require either too many X-ray projections and therefore dose, or are only capable of reconstructing single, curvilinear structures.
Using only two new X-ray projections per 3D reconstruction, we aim to reconstruct more complex arrangements of interventional material than was previously possible.
This is achieved by improving a previously presented deep learning-based reconstruction pipeline, which assumes that the X-ray images are acquired by a continuously rotating biplane system, in two ways: (a) separation of the reconstruction of different object types, (b) motion compensation using spatial transformer networks.
Our pipeline achieves submillimeter accuracy on measured data of a stent and two guidewires inside an anthropomorphic phantom with respiratory motion. In an ablation study, we find that the aforementioned algorithmic changes improve our two figures of merit by 75 % (1.76 mm → 0.44 mm) and 59 % (1.15 mm → 0.47 mm) respectively. A comparison of our measured dose area product (DAP) rate to DAP rates of 2D fluoroscopy indicates a roughly similar dose burden.
This dose efficiency combined with the ability to reconstruct complex arrangements of interventional material makes the presented algorithm a promising candidate to enable 3D fluoroscopy.
血管疾病通常采用微创方法进行治疗。在这些经皮介入中使用的介入材料（支架、导丝等）通过某种形式的图像引导来进行可视化。目前，这种图像引导通常由二维 X 射线透视（即实时二维图像）提供。三维 X 射线透视（即实时三维图像）可以加速现有的干预措施并实现新的干预措施。然而，现有的介入材料三维重建算法要么需要太多的 X 射线投影，因此需要剂量，要么只能重建单个曲线结构。
我们旨在使用每个三维重建仅需两个新的 X 射线投影，重建比以前更复杂的介入材料排列。
这是通过改进之前提出的基于深度学习的重建管道来实现的，该管道假设 X 射线图像是通过连续旋转的双平面系统获取的，方法是：（a）分离不同物体类型的重建，（b）使用空间变换网络进行运动补偿。
我们的管道在具有呼吸运动的人体模型内对支架和两条导丝的测量数据实现了亚毫米精度。在消融研究中，我们发现上述算法变化分别将我们的两个质量指标提高了 75%（1.76 毫米→0.44 毫米）和 59%（1.15 毫米→0.47 毫米）。我们的测量剂量面积乘积（DAP）率与二维透视的 DAP 率的比较表明，剂量负担大致相似。
这种剂量效率与重建介入材料复杂排列的能力相结合，使得所提出的算法成为实现三维透视的有前途的候选者。
